English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Incorporating prior knowledge like lexical constraints into the model'soutput to generate meaningful and coherent sentences has many applications indialogue system, machine translation, image captioning, etc. However, existingRNN-based models incrementally generate sentences from left to right via beamsearch, which makes it difficult to directly introduce lexical constraints intothe generated sentences. In this paper, we propose a new algorithmic framework,dubbed BFGAN, to address this challenge. Specifically, we employ a backwardgenerator and a forward generator to generate lexically constrained sentencestogether, and use a discriminator to guide the joint training of two generatorsby assigning them reward signals. Due to the difficulty of BFGAN training, wepropose several training techniques to make the training process more stableand efficient. Our extensive experiments on two large-scale datasets with humanevaluation demonstrate that BFGAN has significant improvements over previousmethods.

BFGAN: Backward and Forward Generative Adversarial Networks for Lexically Constrained Sentence Generation